daikali407/Qwen2.5-7B-Instruct

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 5, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen2.5-7B-Instruct is a 7.61 billion parameter instruction-tuned causal language model from the Qwen2.5 series, developed by Qwen. It features a 131,072-token context length and excels in coding, mathematics, instruction following, and generating long, structured outputs like JSON. This model also offers robust multilingual support for over 29 languages.

Loading preview...

Qwen2.5-7B-Instruct Overview

Qwen2.5-7B-Instruct is an instruction-tuned causal language model from the Qwen2.5 series, featuring 7.61 billion parameters and a substantial 131,072-token context length. Developed by Qwen, this model builds upon the Qwen2 architecture with significant enhancements across several key areas.

Key Capabilities and Improvements

  • Enhanced Knowledge & Reasoning: Demonstrates significantly improved capabilities in coding and mathematics, leveraging specialized expert models.
  • Instruction Following: Offers substantial improvements in adhering to instructions, generating long texts (over 8K tokens), and understanding structured data such as tables.
  • Structured Output Generation: Excels at producing structured outputs, particularly JSON, and is more resilient to diverse system prompts, enhancing role-play and condition-setting for chatbots.
  • Long-Context Support: Supports a full context length of 131,072 tokens and can generate up to 8,192 tokens. It utilizes YaRN for effective long-text processing, though users should note potential performance impacts on shorter texts if YaRN is statically enabled.
  • Multilingual Support: Provides robust support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.

Architecture and Features

This model is built on a transformer architecture, incorporating RoPE, SwiGLU, RMSNorm, and Attention QKV bias. It has 28 layers and 28 attention heads (with 4 for KV in GQA configuration). For optimal performance, it is recommended to use transformers version 4.37.0 or newer.

Finetunes
1 models